Fix mlx_lm.server --adapter-path silently ignored at startup#1249
Open
odysa wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #1248.
ModelProvider.load("default_model", ...)overwritesmodel_pathwith the resolved real path before looking up_adapter_map. Since_adapter_mapis keyed by the alias"default_model", the lookup misses and the CLI-provided--adapter-pathsilently falls back toNone.Fix: resolve
adapter_pathusing the alias key before reassigningmodel_path.Repro
Before fix — bogus adapter path is silently dropped:
mlx_lm.server --model mlx-community/Qwen2.5-0.5B-Instruct-4bit --adapter-path /tmp/does-not-exist # Server starts cleanly.After fix — same command raises
FileNotFoundError: The adapter path does not exist: /tmp/does-not-exist, matching the behavior of the per-request HTTP API.